New issue
Advanced search Search tips
Note: Color blocks (like or ) mean that a user may not be available. Tooltip shows the reason.

Issue 718776 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 718752
Owner: ----
Closed: May 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

32.8% regression in blink_perf.canvas at 468696:468789

Project Member Reported by kraynov@chromium.org, May 5 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=718776

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgip7_sAoM


Bot(s) for this bug's original alert(s):

chromium-rel-win7-gpu-ati
Mergedinto: 718752
Status: Duplicate (was: Untriaged)

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : zakerinasab
  Commit : 4c4a925b1a047a296b7962566ff63918f3eba1c4
  Date   : Tue May 02 20:34:28 2017
  Subject: Add performance test for ImageData.dataUnion

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : blink_perf.canvas
  Metric       : getImageData/getImageData
  Change       : 34.19% | 318.482143792 -> 209.597186481

Revision             Result                  N
chromium@468763      318.482 +- 8.80386      6      good
chromium@468764      206.259 +- 7.42726      6      bad       <--
chromium@468765      206.141 +- 2.48659      6      bad
chromium@468767      206.315 +- 2.23434      6      bad
chromium@468770      206.708 +- 2.81383      6      bad
chromium@468776      210.639 +- 6.45073      6      bad
chromium@468789      209.597 +- 4.91805      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.canvas

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980441719318333472

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5890599477051392


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!

=== BISECT JOB RESULTS ===
Bisect was unable to run to completion

The bisect was able to narrow the range, you can try running with:
  good_revision: 3f5e8d10f9ab29fee3f8b02c4b889bec8e3d4845
  bad_revision : 5e17a9358f03488e71cba7c4b6786afba95fed6e

If failures persist contact the team (see below) and report the error.


Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : blink_perf.canvas
  Metric       : getImageData/getImageData
  Change       : 34.65% | 314.504860278 -> 205.519178599

Revision             Result                  N
chromium@468695      314.505 +- 8.57266      6      good
chromium@468742      317.274 +- 9.88839      6      good
chromium@468754      313.271 +- 14.861       6      good
chromium@468760      314.512 +- 12.4719      6      good
chromium@468763      315.418 +- 9.56296      6      good
chromium@468765      206.425 +- 7.43914      6      bad
chromium@468766      205.991 +- 3.12136      6      bad
chromium@468789      205.519 +- 2.01031      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.canvas

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980441736469960368

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6398887650131968


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : zakerinasab
  Commit : 4c4a925b1a047a296b7962566ff63918f3eba1c4
  Date   : Tue May 02 20:34:28 2017
  Subject: Add performance test for ImageData.dataUnion

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : blink_perf.canvas
  Metric       : getImageData/getImageData
  Change       : 34.11% | 319.5183164 -> 210.537785087

Revision             Result                  N
chromium@468695      319.518 +- 11.4905      6      good
chromium@468742      315.695 +- 9.13546      6      good
chromium@468754      316.941 +- 10.1526      6      good
chromium@468760      315.646 +- 11.2422      6      good
chromium@468763      316.973 +- 11.7291      6      good
chromium@468764      208.393 +- 6.99432      6      bad       <--
chromium@468765      205.155 +- 1.59472      6      bad
chromium@468766      208.116 +- 9.22315      6      bad
chromium@468789      210.538 +- 7.24535      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.canvas

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980431920694649920

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6398887650131968


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!

Sign in to add a comment